Detail publikace

Extraction of Retina Features Based on Position of the Blood Vessel Bifurcation

Originální název

Extraction of Retina Features Based on Position of the Blood Vessel Bifurcation

Anglický název

Extraction of Retina Features Based on Position of the Blood Vessel Bifurcation

Jazyk

en

Originální abstrakt

This paper deals with a proposal of the algorithm for features extraction from the blood vessels on the back of eyeball. Automated extraction is based on the bifurcations (points where a single vessel splits into two vessels) in retina. Each particular bifurcation is subsequently specified by its own position given by the coordinate system derived from the mutual position of the optic disc and fovea. The complete algorithm has been developed in C++ language and uses OpenCV library for image processing. This proposed method was evaluated on available images of the STARE and DRIVE databases.

Anglický abstrakt

This paper deals with a proposal of the algorithm for features extraction from the blood vessels on the back of eyeball. Automated extraction is based on the bifurcations (points where a single vessel splits into two vessels) in retina. Each particular bifurcation is subsequently specified by its own position given by the coordinate system derived from the mutual position of the optic disc and fovea. The complete algorithm has been developed in C++ language and uses OpenCV library for image processing. This proposed method was evaluated on available images of the STARE and DRIVE databases.

BibTex


@article{BUT105970,
  author="Josef {Hájek} and Martin {Drahanský} and Radek {Drozd}",
  title="Extraction of Retina Features Based on Position of the Blood Vessel Bifurcation",
  annote="This paper deals with a proposal of the algorithm for features extraction from
the blood vessels on the back of eyeball. Automated extraction is based on the
bifurcations (points where a single vessel splits into two vessels) in retina.
Each particular bifurcation is subsequently specified by its own position given
by the coordinate system derived from the mutual position of the optic disc and
fovea. The complete algorithm has been developed in C++ language and uses OpenCV
library for image processing. This proposed method was evaluated on available
images of the STARE and DRIVE databases.",
  address="The World Academic Publishing Co.",
  booktitle="Journal of Medical Research and Development",
  chapter="105970",
  edition="NEUVEDEN",
  howpublished="print",
  institution="The World Academic Publishing Co.",
  number="3",
  volume="2",
  year="2013",
  month="june",
  pages="55--59",
  publisher="The World Academic Publishing Co.",
  type="journal article - other"
}